© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3526
    Prev
    Next
    INDEX
    Explanations

    the methodology of casting a spell on a creature or target

    oai_token-act-pair · gemini-2.0-flash

    Cast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.86
    AccessorTable
    -0.82
    AddTagHelper
    -0.82
    ReusableCell
    -0.79
     viewType
    -0.79
    RectangleBorder
    -0.76
    ISupport
    -0.72
    multer
    -0.71
    MENAFN
    -0.71
     NSCoder
    -0.70
    POSITIVE LOGITS
     magia
    0.48
    <bos>
    0.47
    tillinger
    0.46
    andalf
    0.46
    Words
    0.44
    reflect
    0.44
    scryfall
    0.43
    words
    0.43
     cards
    0.41
     maske
    0.41
    Activations Density 0.947%

    No Known Activations